oookayamaswallow's picture
回しなおしたのでpush
503b8e5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9279464483261108,
"min": 0.9279464483261108,
"max": 2.8677165508270264,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8870.240234375,
"min": 8870.240234375,
"max": 29431.375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.866422653198242,
"min": 0.523067057132721,
"max": 12.866422653198242,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.952392578125,
"min": 101.47500610351562,
"max": 2603.08154296875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07161606462661403,
"min": 0.059430613687293896,
"max": 0.07543190238499722,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2864642585064561,
"min": 0.24383551273072668,
"max": 0.3664145125127535,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19725944554688885,
"min": 0.13280159980286937,
"max": 0.2857901934315176,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7890377821875554,
"min": 0.5312063992114775,
"max": 1.4289509671575882,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.386363636363637,
"min": 3.772727272727273,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 166.0,
"max": 1394.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.772727272727273,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 166.0,
"max": 1394.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1722437511",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722437955"
},
"total": 444.19406977899996,
"count": 1,
"self": 0.4393552169999566,
"children": {
"run_training.setup": {
"total": 0.05927546500004155,
"count": 1,
"self": 0.05927546500004155
},
"TrainerController.start_learning": {
"total": 443.69543909699996,
"count": 1,
"self": 0.552766290995578,
"children": {
"TrainerController._reset_env": {
"total": 2.6011603629999627,
"count": 1,
"self": 2.6011603629999627
},
"TrainerController.advance": {
"total": 440.44331370600446,
"count": 18203,
"self": 0.2658895780105013,
"children": {
"env_step": {
"total": 440.17742412799396,
"count": 18203,
"self": 282.4349340459853,
"children": {
"SubprocessEnvManager._take_step": {
"total": 157.46905357400078,
"count": 18203,
"self": 1.4491038109950978,
"children": {
"TorchPolicy.evaluate": {
"total": 156.01994976300568,
"count": 18203,
"self": 156.01994976300568
}
}
},
"workers": {
"total": 0.273436508007876,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 442.5050466840081,
"count": 18203,
"is_parallel": true,
"self": 226.02941221299625,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005070621000072606,
"count": 1,
"is_parallel": true,
"self": 0.0034363440001925483,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016342769998800577,
"count": 10,
"is_parallel": true,
"self": 0.0016342769998800577
}
}
},
"UnityEnvironment.step": {
"total": 0.03632970800003932,
"count": 1,
"is_parallel": true,
"self": 0.0006902890002038475,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039318599999660364,
"count": 1,
"is_parallel": true,
"self": 0.00039318599999660364
},
"communicator.exchange": {
"total": 0.03314641399992979,
"count": 1,
"is_parallel": true,
"self": 0.03314641399992979
},
"steps_from_proto": {
"total": 0.0020998189999090755,
"count": 1,
"is_parallel": true,
"self": 0.0004139989998748206,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001685820000034255,
"count": 10,
"is_parallel": true,
"self": 0.001685820000034255
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 216.47563447101186,
"count": 18202,
"is_parallel": true,
"self": 10.03200970801845,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.421959038996306,
"count": 18202,
"is_parallel": true,
"self": 5.421959038996306
},
"communicator.exchange": {
"total": 167.45527470798493,
"count": 18202,
"is_parallel": true,
"self": 167.45527470798493
},
"steps_from_proto": {
"total": 33.566391016012176,
"count": 18202,
"is_parallel": true,
"self": 6.409855371027106,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.15653564498507,
"count": 182020,
"is_parallel": true,
"self": 27.15653564498507
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012729999991734076,
"count": 1,
"self": 0.00012729999991734076,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.8873482930567,
"count": 664273,
"is_parallel": true,
"self": 14.27057802308559,
"children": {
"process_trajectory": {
"total": 238.71339789897104,
"count": 664273,
"is_parallel": true,
"self": 237.831125574971,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8822723240000414,
"count": 4,
"is_parallel": true,
"self": 0.8822723240000414
}
}
},
"_update_policy": {
"total": 181.90337237100005,
"count": 90,
"is_parallel": true,
"self": 56.46925150899801,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.43412086200203,
"count": 4584,
"is_parallel": true,
"self": 125.43412086200203
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09807143700004417,
"count": 1,
"self": 0.001021087000026455,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09705035000001772,
"count": 1,
"self": 0.09705035000001772
}
}
}
}
}
}
}